• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Arabian Journal for Science and Engineering. Section A, Sciences >Bad Smell Detection Using Machine Learning Techniques: A Systematic Literature Review
【24h】

Bad Smell Detection Using Machine Learning Techniques: A Systematic Literature Review

机译：使用机器学习技术的不良气味检测：系统文献综述

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Code smells are indicators of potential problems in software. They tend to have a negative impact on software quality. Severalstudies use machine learning techniques to detect bad smells. The objective of this study is to systematically review andanalyze machine learning techniques used to detect code smells to provide interested research community with knowledgeabout the adopted techniques and practices for code smells detection. We use a systematic literature review approach toreview studies that use machine learning techniques to detect code smells. Seventeen primary studies were identified. Wefound that 27 code smells were used in the identified studies; God Class and Long Method, Feature Envy, and Data Classare the most frequently detected code smells. In addition, we found that 16 machine learning algorithms were employed todetect code smells with acceptable prediction accuracy. Furthermore, we the results also indicate that support vector machinetechniques were investigated the most. Moreover, we observed that J48 and Random Forest algorithms outperform the otheralgorithms. We also noticed that, in some cases, the use of boosting techniques on the models does not always enhance theirperformance. More studies are needed to consider the use of ensemble learning techniques, multiclassification, and featureselection technique for code smells detection. Thus, the application of machine learning algorithms to detect code smellsin systems is still in its infancy and needs more research to facilitate the employment of machine learning algorithms indetecting code smells.
机译：代码气味是软件中潜在问题的指示。它们往往会对软件质量产生负面影响。一些研究使用机器学习技术来检测难闻的气味。这项研究的目的是系统地审查和分析用于检测代码气味的机器学习技术，以向感兴趣的研究社区提供有关所采用的代码气味检测技术和实践的知识。我们使用系统的文献综述方法来综述使用机器学习技术检测代码气味的研究。确定了十七项主要研究。我们发现，在已识别的研究中使用了27种代码气味。上帝类别和长方法，功能嫉妒和数据类别是最常检测到的代码气味。此外，我们发现采用16种机器学习算法以可接受的预测精度检测代码气味。此外，我们的结果还表明，对支持向量机技术的研究最多。此外，我们观察到J48算法和随机森林算法的性能优于其他算法。我们还注意到，在某些情况下，在模型上使用增强技术并不总是可以提高其性能。需要更多的研究来考虑使用集成学习技术，多分类和特征选择技术来检测代码气味。因此，机器学习算法在系统中检测代码气味的应用仍处于起步阶段，需要进一步研究以促进机器学习算法在检测代码气味方面的应用。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号